© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11948
    Prev
    Next
    INDEX
    Explanations

    phrases expressing a suggested solution or a workaround, and often used in technical contexts

    oai_token-act-pair · gemini-2.0-flash

    context of a task or solution

    np_token-act-pair-logits · gpt-4o-mini

    work

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyVersion
    -0.67
     Phry
    -0.62
     thiệu
    -0.62
    BrowserModule
    -0.59
    
    -0.59
     WaitForSeconds
    -0.57
    ússia
    -0.57
    oher
    -0.56
    mallows
    -0.56
    ^(@)
    -0.56
    POSITIVE LOGITS
     work
    0.52
    \{\\
    0.49
     WORK
    0.48
    sendFile
    0.46
    CloseOperation
    0.43
     Work
    0.43
    Skocz
    0.43
    AccessorTable
    0.42
     estekak
    0.42
    hou
    0.42
    Activations Density 2.731%

    No Known Activations